Kokoro TTS

Lightweight, high-quality open source text-to-speech model

Audio & MusicFree

Kokoro is a high-quality, open-weight text-to-speech model known for its small size and fast inference speed while producing natural-sounding speech. It supports multiple voices and can run efficiently on consumer hardware. Developers and researchers use Kokoro as a practical, free alternative to commercial TTS services for local inference, application development, and speech synthesis research.

Key Features

• ✓High quality TTS
• ✓Small model size
• ✓Fast inference
• ✓Multiple voices
• ✓Open weights
• ✓Local inference